Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129802
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realmente
    -0.08
     routes
    -0.07
     naprawdę
    -0.07
     olm
    -0.07
     dotenv
    -0.07
     הנ
    -0.07
     Kell
    -0.07
     nails
    -0.07
     Ob
    -0.07
     ספ
    -0.07
    POSITIVE LOGITS
    :+
    0.10
    ريان
    0.09
    itl
    0.08
    (undefined
    0.08
    Assign
    0.08
    (pd
    0.08
    สวน
    0.07
    Analog
    0.07
     ბავშვ
    0.07
    ("",
    0.07
    Activations Density 0.008%

    No Known Activations